Can AI help us repair our cameras? A test request on my own behalf

[Andreas Thaler]

Artificial intelligence (AI) could also be helpful in finding information about camera repairs.

To get an idea, I asked ChatGPT (App for iOS) for information about me and the Canon T90 (my current focus), as that's the best way to judge the quality.

My search query was

andreas thaler canon t90 service and repair


The result:

Andreas Thaler is a skilled camera technician based in Vienna, Austria, renowned for his extensive work on repairing and restoring the Canon T90, a classic 35mm manual-focus SLR introduced in 1986. He has shared his in-depth knowledge and repair techniques on various photography forums, particularly on Photrio.com, where he has documented solutions to common T90 issues.

Common Canon T90 Issues Addressed by Andreas Thaler

Thaler has tackled several prevalent problems with the Canon T90, including:

• Sticky Shutter Blades: Over time, the shutter blades can become sticky due to deteriorating dampers. Thaler has developed methods to clean and restore these components, often employing acetone and precision tools for disassembly.
• HELP/EEE Error Messages: These errors typically indicate a malfunctioning shutter mechanism. Thaler has provided systematic troubleshooting steps to diagnose and resolve these issues, often without the need for full shutter replacement.
• Battery Compartment Corrosion: Leaked battery electrolytes can damage the battery compartment. Thaler has shared techniques for cleaning and restoring these areas to ensure proper functionality.

Repair Services in Vienna

While Thaler does not operate a formal repair service, his extensive contributions to the T90 repair community have been invaluable. For those seeking professional repair services in Vienna, the following establishments are recommended:

Microservice GmbH

Closed · Repair Service

Wiedner Gürtel 46a, 1040 Wien

Provides repair services for various Canon devices, including cameras.

It’s advisable to contact these service centers in advance to confirm their ability to repair the Canon T90, as parts for this model may be limited.


Further Resources

For those interested in undertaking DIY repairs or learning more about the Canon T90, the following resources are recommended:

• Photrio.com Forum: A community where Andreas Thaler and other enthusiasts share repair techniques and solutions for the Canon T90.
• Canon T90 Service Manual: A comprehensive guide providing detailed information on the T90’s components and repair procedures.

If you require assistance in locating specific parts or have questions about the repair process, feel free to ask.

Comments

• It's amazing what AI can quickly gather when querying the web.
• If I were vain, I'm of course not I would be pleased with this very positive portrayal of myself.
• But that also makes the whole thing suspicious. Because whether this assessment is accurate or not can only be determined by what I write under my own name and what others might write about me.
• Whether this makes sense or nonsense is something the AI can't judge, how could it? For that, AI would have to sit down at the desk itself with a screwdriver
• It reminds me of the days before Google, when metasearch engines were used, querying multiple search engines in parallel to improve search results.
• The AI doesn't do anything else here except summarize the results in one text, with the sources cited in the app.
• I find the judgment and tone questionable. What are you supposed to believe if you read this?

---

Now a search query only on a subject without mentioning a person:

canon t90 eee help


The result:

The EEE / HELP error on the Canon T90 is a common and frustrating issue. It indicates a shutter-related malfunction, often caused by mechanical or electrical failure. Here’s a guide to understanding and addressing this problem:

What Causes the EEE / HELP Error?

1. Sticky shutter blades – Often due to degraded dampers inside the shutter mechanism (Copal Square S).
2. Weak or failed magnets (MG1/MG2) – These control shutter movement and release.
3. Faulty TR1 transistor – Controls current to the shutter magnets.
4. Charge motor (M2) failure or stiffness – Essential for cocking the shutter.
5. Dried-out lubrication or internal corrosion – Especially from leaked batteries.

Andreas Thaler’s Recommended Troubleshooting (Summarized from Photrio)

Andreas Thaler has published several detailed posts on Photrio.com outlining how to diagnose and fix this. Here are the essentials:

1. Check the Charge Motor (M2)

• Listen if the motor runs when the shutter button is pressed.
• If the motor sounds weak or doesn’t turn, it may need cleaning or replacement.

2. Clean the Shutter Blades

• Disassemble the top plate to access the shutter mechanism.
• Use acetone and fine tools (like a toothpick or brush) to clean sticky blades.
• CAUTION: Requires precision – not recommended unless you’re experienced.

3. Test Shutter Magnets

• MG1 and MG2 can lose magnetism over time or be mechanically blocked.
• Use a multimeter to test continuity and signal.
• Clean the magnet surfaces carefully if contaminated.

4. Test Transistor TR1

• This transistor can fail and cause shutter release issues.
• Use a multimeter in diode mode to check forward/reverse bias of the transistor.

DIY vs. Professional Repair

• DIY Repair: Only recommended if you’re familiar with electronics and fine mechanical systems.
• Professional Repair: Parts for the T90 are rare; contacting someone like Andreas Thaler (via Photrio) may yield guidance or help.

Resources

• Photrio T90 Troubleshooting Thread (Thaler)
• Canon T90 Service Manual (PDF)

Would you like a visual guide or a step-by-step breakdown for any of these steps?

Comments

• This makes it clearer that AI cannot yet replace the repair man.
• What's written here is partly true, but partly not. It's compiled from various web posts, primarily on PHOTRIO. Working through it in this order won't necessarily solve EEE/HELP, but it's close. Provided the information retrieved and compiled from the web isn't nonsense.
• That is, as long as there's only one source and no contradictions/opposing opinions, the AI itself won't communicate anything different from what it finds.

---

Conclusion

• I haven't delved further into AI yet; this was my first foray into a subject area where I know something.
• The results are helpful, but not miraculous. It's understandable how they're generated and what they depend on.
• Therefore, I'll use AI to search for information on camera repairs, but I'll approach the results with skepticism and try to verify/falsify them.
• In any case, AI doesn't do anything on its own—yet.
• If I can't judge information for truth or falsehood, I won't be successful. And that requires reliable knowledge.

 

[mshchem]

Fascinating, not surprising.

Today I listened while my wife was talking to AI that she thought was human, it was hilarious. Didn't take a minute before the robot gave up and sent her to an actual human.

I understood my dear wife, I've had experience, made sense to me.

 

[Andreas Thaler]

Fascinating, not surprising.

Today I listened while my wife was talking to AI that she thought was human, it was hilarious. Didn't take a minute before the robot gave up and sent her to an actual human.

I understood my dear wife, I've had experience, made sense to me.

Was it Alexa?

 

[Chan Tran]

Ask ChatGPT this "what is 2343234323*23432943232" and see if it has the correct answer. Microsoft Copilot did it wrong. It gives a close answer but not correct. It's wrong in the 5th significant digit. So not as accurate as an 8 digit calculator.

 

[Truzi]

Is the web claiming you are AI? LOL.

Most of the popular AI programs we hear about mention "language models." A large part of this is being able to mimic conversational text (which things were doing well over 15 years ago, but not called AI).

I think it reminds you of the meta-searches because it is very similar - just taken to a higher degree because advances make it possible. It's just a web search that gives you a frequently inaccurate summary narrative instead of only returning links. The "value add" of AI is condensing several sources into blocks of text that seem like someone responded to you in a conversational manner. Someone who has the source text in front of them, but still gets it wrong.

(No it's not!!! It's new, it's shiny, it's different. It's exactly what the marketing tells us it is (despite what experience, observation, and actual tech data from AI firms themselves state.))

 

[Kino]

AI is that neighbor who knows just enough to get you in trouble...

 

[mshchem]

Was it Alexa?

Nope, it was an US division of the drug company Eli Lilly. I had overheard at the beginning "It" identify as AI, my wife missed that part and started a conversation, the robot sounded like a human, neutral US accent amazing. My dear wife is an artist and depending on the situation uses my last name, her last name or her legal last name (hers-mine).

As she was telling the Silicon based life for these details Ms. AI started to rock back and forth with smoke coming out of her head and passed the call off to a human.

At this point my wife turned to me and said, "That was AI".

We are going like lambs to the slaughter. As fast as things can change in one's government, the AI thing will be faster.

 

[Andreas Thaler]

We are going like lambs to the slaughter. As fast as things can change in one's government, the AI thing will be faster.

I have long been receiving my orders from HAL, who speaks to me through my cameras

 

[blee1996]

Hi @Andreas Thaler for more fact based AI assistance, I found perplexity slightly more useful than chatGPT or Claude. You might want to give it a go as well. So this is the response to your question "canon t90 eee help", can you check if it is more or less accurate and useful?

https://www.perplexity.ai/search/canon-t90-eee-help-oO8GJXaSTWiBTBJgPohb9w

 

[Andreas Thaler]

Hi @Andreas Thaler for more fact based AI assistance, I found perplexity slightly more useful than chatGPT or Claude. You might want to give it a go as well. So this is the response to your question "canon t90 eee help", can you check if it is more or less accurate and useful?

https://www.perplexity.ai/search/canon-t90-eee-help-oO8GJXaSTWiBTBJgPohb9w

I'm speechless! I'll be using this to write my posts from now on!

In particular, there are no embarrassing praises for people.

Is this available for the iPhone?

I'll have to check right away.

Thank you!

 

[blee1996]

I'm speechless! I'll be using this to write my posts from now on!

In particular, there are no embarrassing praises for people.

Is this available for the iPhone?

I'll have to check right away.

Thank you!

Yes it has app for both iOS and Android. Although the Pro plan does charge $20 a month.

 

[Andreas Thaler]

You just have to ask Perplexity the right questions!

Summary:
Andreas Thaler is a respected voice in the Canon T90 community, offering practical advice on buying, maintaining, and repairing this iconic camera, which remains a favorite among film enthusiasts for its build quality and advanced features.

But that only happens when I enter my name + Canon T90.

But how does the AI come to such a conclusion? It can't measure the quality of what I write.

That interests me; I'll have to enter the namens of my friends right away to see if they're also respected voices

 

[Andreas Thaler]

Yes it has app for both iOS and Android. Although the Pro plan does charge $20 a month.

I'll gain experience with it and use the app to research information on repair projects. Maybe it'll find more than I can with Google.

 

[Andreas Thaler]

(No it's not!!! It's new, it's shiny, it's different. It's exactly what the marketing tells us it is (despite what experience, observation, and actual tech data from AI firms themselves state.))

Profiting from the work of others - AI fits our times

 

[Andreas Thaler]

AI is that neighbor who knows just enough to get you in trouble...

But you can also use it to defend yourself against this neighbor

 

[Andreas Thaler]

Ask ChatGPT this "what is 2343234323*23432943232" and see if it has the correct answer. Microsoft Copilot did it wrong. It gives a close answer but not correct. It's wrong in the 5th significant digit. So not as accurate as an 8 digit calculator.

There's probably still a Pentium processor working there that has been overseen

 

[BHuij]

I work in data engineering and analytics. The number of people who think AI is the future of software engineering (or writing code of any sort, even SQL queries or data models) is frightening. Given a sufficiently good foundation, Claude and even ChatGPT can save some time writing simple but tedious queries or scripts, provided you're willing to properly evaluate and QA the output to make sure it's actually doing what you want. In my case, I'd rather write the code myself than essentially debug code written by "someone else" about 9 times out of 10.

But as professionals who know what they're doing move out of the workforce, and the source material used to train these large language models becomes increasingly cannibalistic (AIs learning to code by ingesting bad code spit out by other AIs), we're going to end up in a situation where software companies have entire code bases that were written by AI, have fundamental problems, and nobody is left who knows enough to fix them.

 

[Chan Tran]

There's probably still a Pentium processor working there that has been overseen

Out of curiousity I argued with it and said that it was wrong. Found out it did the calculation using scientific notation and it did right but when converting to standard notation it made mistake. I don't know how it changed the mantisa when it did the conversion.

 

[Truzi]

I had a discussion with ChatGPT about The Great Tomsoni - someone I knew a little about because I was into magic back in high school.

It got nothing right, except that he was a Magician. A google search will return the correct result in the first hit.
ChatGPT kept apologizing, telling me I was correct, adding more incorrect information in the process. The browser session eventually crashed, lol.

The only reason I had even done that is because I was in Security training as part of my IT job, and the consultant who came in kept referring to ChatGPT to get answers to example questions. GPT was often incorrect (using common sense) and if we searched actual web pages we'd find the correct answer. Still, the consultant, who had been doing IT since the 90s, often deferred to the chatbot.

 

[BHuij]

Out of curiousity I argued with it and said that it was wrong. Found out it did the calculation using scientific notation and it did right but when converting to standard notation it made mistake. I don't know how it changed the mantisa when it did the conversion.

All these AIs are large language models, not large math models. The process used to train them is ultimately about how effectively they return an output that the user likes or agrees with, with little regard for whether or not it's factually accurate. Now of course, most users will have a more favorable response to a factually accurate response than a factually inaccurate one. But asking a large language model to do math problems is like asking an automatic calculator to write a novel. It's just not the best tool for the job. Doesn't mean it won't get things right frequently, just that it has a high probability of confidently giving you an answer that is "kinda close and definitely believable but ultimately wrong."

 

[Andreas Thaler]

Where I rely on AI is translating my German posts here into English.

Google Translate does that, and I intervene where I think it's necessary.

It's quick, no one has complained yet, and I suspect it's US English that Google returns to me.

 

[BHuij]

Where I rely on AI is translating my German posts here into English.

Google Translate does that, and I intervene where I think it's necessary.

It's quick, no one has complained yet, and I suspect it's US English that Google returns to me.

Even before AI, translation algorithms between major languages were really quite good. I think making them even better is a perfect use case for LLMs.

 

[Truzi]

Where I rely on AI is translating my German posts here into English.

Google Translate does that, and I intervene where I think it's necessary.

It's quick, no one has complained yet, and I suspect it's US English that Google returns to me.

If the translation makes sense, it's probably not US English, lol.

 

[Sharktooth]

Wow! Perplexity is very useful. I just did a search for "Kodak Retina IIIc exposure counter repair". It provided quite a bit of useful information, and also found a link here in Photrio where I asked the same question a while ago. The folks here at Photrio provided the answer for me.

This was infinitely better than a Google search.

 

[blee1996]

Yes I agree: Perplexity has done well with combining search and AI summarization, while reducing hallucination (making up stuff). For some use cases, Perplexity can do better than Google Search.

We still need to cross-verify what AI says, since hallucination is inevitable (even though can be minimized).